AI Wall Thickness Estimation via 4D Angiography

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional methods for estimating the thickness of cerebral aneurysm walls are invasive and provide inaccurate information, making it difficult to propose effective treatments for vascular diseases.

Innovation Solution

A wall thickness estimation method using four-dimensional angiography to capture videos of organ or blood vessel walls, generating behavioral information about changes over time, and using a trained model to visualize thickness at specific points, allowing for accurate visualization and output of thickness information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If craniotomy is performed for visual inspection of aneurysm wall thickness, then measurement precision is improved, but the method becomes highly invasive and places heavy burden on the patient

Engineering Contradiction:

Improveaneurysm wall thickness measurement precisionVSAvoidinvasiveness and patient burden

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent replaces the mechanical surgical approach (craniotomy) with a non-invasive imaging-based system using four-dimensional angiography and AI processing to estimate aneurysm wall thickness, thereby eliminating the harmful effects of surgical invasion while maintaining measurement capability

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces behavioral information about wall movement as an intermediary parameter that correlates with wall thickness. Instead of directly measuring thickness through surgery, the system uses motion characteristics captured by four-dimensional angiography as a proxy indicator

Inventive Principle:

Principle #24Intermediary (Mediator)

2Object-affected harmful factors

If conventional ultrasonic diagnostic apparatus is used to measure blood vessel wall thickness, then the method becomes minimally invasive, but measurement precision deteriorates

Engineering Contradiction:

ImproveinvasivenessVSAvoidblood vessel wall thickness precision

Core Design Contradiction:

Object-affected harmful factorsVSMeasurement precision

Solution Approach 1:

The patent captures dynamic behavioral information about wall movement during the cardiac cycle using four-dimensional angiography, rather than relying on static ultrasonic images. This dynamic approach provides more precise measurements by analyzing motion patterns across multiple time points

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent changes the measurement parameter from direct thickness measurement (which is imprecise with conventional ultrasound) to behavioral information about wall movement. The trained AI model then converts this behavioral information into accurate thickness estimates

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If four-dimensional angiography with trained model is used to estimate wall thickness, then measurement precision is improved, but device complexity increases

Engineering Contradiction:

Improvewall thickness estimation precisionVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent performs preliminary training of the AI model using datasets containing both behavioral information and ground truth thickness measurements. This pre-training phase creates a ready-to-use model that can be deployed without real-time complexity, as the complex learning process is completed beforehand

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent uses four-dimensional angiography to create a behavioral information copy or representation of the actual wall characteristics. This behavioral information serves as a simplified proxy that the AI model processes to derive thickness measurements, avoiding the need for complex direct measurement systems

Inventive Principle:

Principle #26Copying

Data Source

PatentUS20240404056A1Wall thickness estimation method, recording medium, training method, model construction method, wall thickness estimation device, and wall thickness estimation system

Publication Date: 2024.12.05 OSAKA UNIVERSITY

AI summary

A wall thickness estimation method includes: obtaining behavioral information that is based on a video in which an organ wall or a blood vessel wall is captured using four-dimensional angiography, the behavioral information being numerical information about changes over time in a position of each of a plurality of predetermined points in the organ wall or the blood vessel wall; generating estimation information using a model trained to take as an input an image indicating a physical parameter based on the behavioral information obtained in the obtaining and output an index indicating a thickness at each of the plurality of predetermined points in the organ wall or the blood vessel wall, the estimation information being information visualizing the thickness; and outputting the estimation information generated in the generating.